Scholar
Zhiyuan Zhou
Google Scholar ID: unQVOJkAAAAJ
PhD student, UC Berkeley
Citations & Impact
Citations
102
H-index
5
i10-index
5
Publications
11
Co-authors
11
list available
Publications
Resume (English only)
Academic Achievements
- - Paper on Q-chunking published.
- - Paper on Behavior Exploration published.
- - WSRL now works on robots.
- - AutoEval won the Best Paper Award at RSS 2025 Robot Evaluation Workshop.
- - Published a paper on how to do RL fine-tuning without offline data retention, Warm-start RL (WSRL), accepted at ICLR 2025.
- - Led the first big project in his Ph.D., SOAR, which will be presented at CoRL 2024 in Munich.
- - Will present undergraduate work, Tiered Reward: Designing Rewards for Specification and Fast Learning of Desired Behavior, at the RL Conference.
- - Completed undergraduate thesis, Policy Transfer in Lifelong Reinforcement Learning through Learning Generalizing Features.
Research Experience
- - Research intern at Physical Intelligence for the summer.
Education
- - Currently a 3rd year CS Ph.D. student at UC Berkeley, advised by Professor Sergey Levine.
- - Graduated magna cum laude from Brown University with an Sc.B. in Applied Math and Computer Science, where he was advised by Professors George Konidaris and Michael Littman.
Background
- Research Interests: Reinforcement learning, building autonomous generalist robots.
Miscellany
- Personal Interests: Playing guitar, cooking, playing badminton, watching standups and movies.
